Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Movie
    -0.07
     appearance
    -0.07
    μία
    -0.07
    _submission
    -0.06
     하지만
    -0.06
    Gu
    -0.06
     ARC
    -0.06
    _credentials
    -0.06
    ิท
    -0.06
     Paw
    -0.06
    POSITIVE LOGITS
    ="<
    0.07
    uib
    0.07
     мож
    0.06
    TRGL
    0.06
     Alb
    0.06
     трансп
    0.06
     rady
    0.06
     estoy
    0.06
    _salt
    0.06
    нам
    0.06
    Act Density 0.034%

    No Known Activations